4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming healthcare through innovations in mobile and wireless technologies"

Research Article

Classification of Epileptic and Non-Epileptic EEG Events

Download20 downloads
  • @INPROCEEDINGS{10.4108/icst.mobihealth.2014.257352,
        author={Evangelia Pippa and Evangelia Zacharaki and Iosif Mporas and Vasiliki Tsirka and Mark Richardson and Michael Koutroumanidis and Vasileios Megalooikonomou},
        title={Classification of Epileptic and Non-Epileptic EEG Events},
        proceedings={4th International Conference on Wireless Mobile Communication and Healthcare - "Transforming healthcare through innovations in mobile and wireless technologies"},
        publisher={IEEE},
        proceedings_a={MOBIHEALTH},
        year={2014},
        month={12},
        keywords={epileptic seizures; pnes; vasovagal syncope; classification; machine learning},
        doi={10.4108/icst.mobihealth.2014.257352}
    }
    
  • Evangelia Pippa
    Evangelia Zacharaki
    Iosif Mporas
    Vasiliki Tsirka
    Mark Richardson
    Michael Koutroumanidis
    Vasileios Megalooikonomou
    Year: 2014
    Classification of Epileptic and Non-Epileptic EEG Events
    MOBIHEALTH
    IEEE
    DOI: 10.4108/icst.mobihealth.2014.257352
Evangelia Pippa1,*, Evangelia Zacharaki1, Iosif Mporas1, Vasiliki Tsirka2, Mark Richardson2, Michael Koutroumanidis2, Vasileios Megalooikonomou1
  • 1: University of Patras
  • 2: Guy's & St. Thomas' & Evelina Hospital for Children London, UK
*Contact email: pippa@ceid.upatras.gr

Abstract

In this paper, the classification of epileptic and non-epileptic events from multi-channel EEG data is investigated using a large number of time and frequency domain features. In contrast to most of the evaluations found in the literature, in this paper the non-epileptic class consists of two types of paroxysmal episodes of loss of consciousness namely the psychogenic non epileptic seizure (PNES) and the vasovagal syncope (VVS). For the classification, several classification algorithms were explored. The classification models were evaluated on EEG epochs from 11 subjects in an inter-subject cross-validation setting and the best among them achieved classification accuracies of 86% (Bayesian Network), 83% (Random Committee) and 74% (Random Forest).